LLM & Agents

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

This skill teaches the agent how to implement the data access layer in the API project. MANDATORY - You MUST read this skill before modifying any ./api repository files.

Use this skill when working on code projects that need memory persistence, code validation, multi-agent coordination, or workflow tracking. Activates Claude Code Guardian MCP tools.

Git workflow guidelines for AI agents working on this repository

Write effective tests with proper structure and coverage. Use when writing unit tests, integration tests, or improving test quality.

Use after writing-plans to decompose monolithic plan into individual task files and identify tasks that can run in parallel (up to 2 subagents simultaneously)

Memory-First development workflow integrating Serena short-term project memory and Cipher long-term design knowledge for efficient LoRAIro development

Implement RAG systems using Weaviate vector database. Use when building semantic search, document retrieval, or knowledge base systems.

Spawn a Claude worker to address PR feedback, fix CI failures, or continue work on a pull request. Use when a PR needs updates based on review comments or failing checks.

Implement code quality ratchets to prevent proliferation of deprecated patterns. Use when (1) migrating away from legacy code patterns, (2) enforcing gradual codebase improvements, (3) preventing copy-paste proliferation of deprecated practices, or (4) setting up pre-commit hooks to count and limit specific code patterns. A ratchet fails if pattern count exceeds OR falls below expected—ensuring patterns never increase and prompting updates when they decrease.

Homeostatic sensor detecting requirements without implementation or test coverage. Scans for REQ-* keys in requirements docs and checks if they have corresponding code and tests. Use to find coverage gaps.

PR 코드 리뷰, 개선 제안, 자동 머지 에이전트. 코드 품질, 테스트, 보안 검사 통합.

Optimizes ProAgentic development environment by cleaning port conflicts, Docker images, memory issues, and test artifacts. Performs aggressive port cleanup, Docker image optimization, memory monitoring, and system health diagnostics. Use before starting development, when app won't start with port errors, when system feels slow, or for weekly maintenance. Provides before/after metrics and health reports.

Use this skill whenever the user wants to set up, refactor, or optimize Supabase usage in a Next.js (App Router) + TypeScript project, including auth, database, storage, RLS-safe patterns, edge functions, and secure client/server integration.

Product management expertise for story creation, backlog management, validation, and release coordination

Real-time observability dashboard for multi-agent Claude Code sessions.Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts.**Key Features:**- 🔴 Real-time event streaming via WebSocket- 📊 Agent swim lanes showing parallel execution- 🔍 Event filtering by agent, session, event type- 📈 Live charts for tool usage patterns- 💾 Filesystem-based (no database required)**Inspired by [@indydevdan](https://github.com/indydevdan)**'s work on multi-agent observability.**Our approach:** Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.

Automate Git workflow for AgentOS. Handles branch creation, TODO-based commits, and PR generation following project conventions.

智能 Prompt 优化顾问技能。基于 Anthropic 官方最佳实践,通过场景识别和技术匹配,将用户的模糊需求转化为高质量 prompt。触发场景:(1) 用户明确请求"优化 prompt"、"帮我写 prompt"、"改进这个指令";(2) 用户的需求描述模糊、不清晰、缺少关键信息;(3) 用户提到"不知道怎么表达"、"效果不好"等问题。适用于所有需要与 Claude 交互的场景,通过结构化对话挖掘需求,生成符合 Claude 4.5 最佳实践的优化 prompt。

Searches and analyzes bash command history using Atuin CLI integration. Use when finding previously-run commands, analyzing command patterns, searching for cloud/deployment commands, or when mentioned 'bash history', 'atuin', 'command history', 'what command did I use', 'find command'.

テストカバレッジ分析とテスト生成ガイダンス。coverage.jsonを解析し、未カバー行/ブランチを特定、優先度付きテスト作成提案を出力。トリガー: "カバレッジ分析", "coverage analyze", "テストカバレッジ向上", "未カバー行"